跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+2471新增论文
+2025其中 AI 相关
+163已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 20:36 · 全站最近入库：2026-11-10 15:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 21:26 — 2026-11-10 21:26（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-10 20:36最近发现新增版本：2026-11-10 15:22库内论文最新更新时间：2026-11-10 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

20,643 已收录论文17,531 AI 相关5,643 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 16,219 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 20:33（北京时间）
版本更新 · v4arXiv:2604.24357

DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models

Dake Bu, Wei Huang, Andi Han, Si Wu, Hau-San Wong, Qingfu Zhang, Taiji Suzuki, Atsushi Nitanda

原文摘要

Discrete diffusion models admit many token orders, yet most systems rely on confidence-based decoding. Confidence is a strong and efficient heuristic, but it can be myopic because local certainty does not measure a position's effect on terminal quality. We introduce DPRM (Doob h-transform Process Reward Model), a plug-in token-ordering module induced by a terminal-reward-tilted trajectory distribution. The Doob transform converts terminal reward into a process reward for each candidate position. A compact estimator indexed by generation progress, confidence, and optional positional or task state makes this correction reusable across partial states. DPRM changes only token order; the host architecture, denoising objective, supervision, and token sampler remain fixed. We derive the exact reward-tilted law and bound its shortlist and online approximations. Across nine recent open-source hosts spanning language, multimodal generation, and scientific sequences, DPRM improves reasoning, numeric VQA, visual-codebook ordering, and preference-conditioned generation. Relative to confidence, it improves PUMA GSM8K by 14.6%, Omni-Diffusion CLIP-L/14 by 13.2%, Prism voted accuracy from 82.41% to 83.85%, and RealWorldQA numeric/count accuracy by 8.97 points. Matched scientific gains include 8.3% in DCM nonzero recovery, 15.0% in GenMol QED, and 53.3% in SDPO-DNA total utility. Entropy and random-order controls show that the gains do not come from favoring uncertain tokens indiscriminately. Token-order traces and shared-state interventions instead show how terminal reward can correct a locally confident but globally poor choice. Code is available at: https://github.com/DakeBU/DPRM-DLLM.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06320

Conformal Prediction for Distribution-to-Distribution Regression

Trung-Khang Tran, Tuan A. Hoang, Viet-Hoang Tran, Tan M. Nguyen

原文摘要

Conformal Prediction (CP) provides a model-agnostic framework for constructing finite-sample prediction sets with coverage guarantees and has become a tool for reliable decision-making in high-risk settings. Recent advances have extended Split Conformal Prediction to increasingly complex learning problems, including multilabel, high-dimensional, and functional outputs. In this work, we study CP for Distribution-to-Distribution Regression, a setting of growing interest across many application domains. We show that a naive application of Split CP yields prediction sets that, while marginally valid, are non-interpretable, e.g., lacking a well-defined volume or a tractable sampling procedure, and of limited practical value. To overcome this, we propose a new conformal framework that operates in an orthogonal basis space, producing interpretable prediction sets while preserving coverage guarantees. We further develop an adaptive variant with asymptotic conditional coverage under mild assumptions. Empirical results on synthetic and real-world datasets validate the effectiveness of the proposed approach. The code is publicly available at https://github.com/tuanhacs/conformal_d2d.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12648

Maurer-Inspired Two-Way Physical-Layer Authentication Against Multi-Antenna Impersonation Attacks

Pin-Hsun Lin, Linda Senigagliesi, Eduard A. Jorswieck

原文摘要

In this work, we investigate Maurer-inspired two-way physical-layer authentication. Alice seeks authentication by Bob in the presence of a multi-antenna impersonator, Trudy. Trudy may replace the challenge to Alice, the response to Bob, or both. To create an information advantage, Bob adds artificial noise (AN) to his challenge, and Alice adds spatial AN while forwarding the received mixture. Bob predicts the response from trusted preparation, whereas Trudy observes only a noisy version of the challenge, and Alice's AN interferes with Trudy's preparation reception. Impersonation thus requires matching Bob's fresh randomness beyond the channel consistency checked by public-pilot one-way authentication. For quasi-static Gaussian multiple-input multiple-output channels with time-division duplex (TDD) reciprocity, we derive missed-detection bounds for attacks that replace the authentication challenge, the response, or both. These bounds assume attack-free initial training and preparation and account for estimation error and AN leakage. With equal antenna numbers at all nodes, we show scenarios where the proposed scheme has lower worst-case missed detection than specified one-way tests with/without AN.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12646

Surrendering and Reclaiming Judgment: How Software Engineering Students Experience AI Reliance

Nathan Cassee, Umit Akirmak, Luiz Guerra, Margaret-Anne Storey, Neil Ernst

原文摘要

Software architecture is one of the skills novice developers must master to succeed in industry, and as AI disrupts software development, it is also transforming how students learn architecture. Existing work on how students and novices work with AI has mostly focused on small programming exercises or on students' perceptions of AI, so little is known about how students experience AI as they learn software architecture in larger team projects. We report on an exploratory case study of 43 senior software engineering students who used AI throughout a semester-long, team-based software architecture project. We combined surveys with focus groups and analyzed the focus group transcripts and the open survey responses through Braun and Clarke's reflexive thematic analysis. We constructed two themes. The first, Surrendering Judgment to AI, traces how participants' reliance on AI deepened as they used it to architect and implement their systems, until they surrendered their judgment and became stuck in a codebase they had created but could not understand, which made them rely on AI even more. Participants described feeling ashamed, frustrated, and emotionally disconnected from their work, a toll that, in our reading, left them with even less reason to break their reliance. The second, Applying Human Judgment, centers on participants who kept or reclaimed their judgment: the knowledge and experience it rested on, and the strategies they used to apply it. Participants' accounts suggest that relaxed deadlines and a lecture and lab on working with AI gave them room to acquire knowledge and reclaim judgment. Given the expectations placed on junior developers and the widespread adoption of AI, we believe these first-hand accounts can help software engineering education and industry adopt AI in ways that preserve novice developers' judgment, ownership, and motivation.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12643

Simulation-aided Reinforcement Learning with Control Variates

Omer Hemo, Ido Sefi, Mirco Mutti, Aviv Tamar, Kfir Y. Levy

原文摘要

Reinforcement Learning (RL) algorithms often rely on data collected from a target environment, which can be expensive and noisy. Although simulators can generate large amounts of additional data, standard simulation mixing approaches, which directly combine simulated and real experience, can degrade performance due to simulator inaccuracies, especially when they bias the solution away from the optimal policy. We propose a conservative simulation-aided learning method based on control variates, where simulated data is used solely to reduce variance in the learning process rather than directly shaping the learning target. We develop our approach for Policy-Evaluation, which is a fundamental building block of RL algorithms. Then we combine it within the actor-critic framework towards policy improvement, as well as extend it towards offline RL scenarios. Experiments on multiple MuJoCo benchmark tasks demonstrate improvements over standard simulation mixing approaches, highlighting control variates as an effective tool for simulation-aided reinforcement learning.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12640

TrialDesignBench: Benchmarking Language Models for Phase-I Trial Design Against Clinical Knowledge

Yihan Hank Tang, Peng Yang, Jiayi Xin, Tianqi Shang, Xuyang Chen, Ying Yuan, Yi Lian, Qi Long

原文摘要

AI is used in much of the clinical trial pipeline. However, selecting the statistical design of a trial, a crucial step that determines how drug doses are tested on humans and evaluated, has seen almost no AI progress. LLMs appear to be a natural fit given their strengths in biomedical knowledge and statistical reasoning. Nevertheless, there is currently no appropriate way to evaluate such abilities because recent regulatory and methodological shifts, most notably FDA's Project Optimus, have redefined what constitutes a reasonable design and rendered many previous designs obsolete. To lay the groundwork for AI-assisted trial design, we introduce TrialDesignBench, a benchmark of 617 Phase-I/I-II oncology dose-finding trials, each paired with an expert-validated reference design that is consistent with the latest FDA regulatory initiatives. This reference standard is produced through a formalization of the expert design process. We evaluate five frontier LLMs, none of which matches the reference standard. Our ablation experiments trace this performance gap to two main causes, inference of latent, unrecorded design determinants from trial sources (supplying them raises class-wise balanced accuracy by 0.22) and structured decision-tree reasoning (+0.24). TrialDesignBench offers a reproducible, contemporary-standard objective for evaluating and enhancing AI-assisted trial design.

cs.AI · cs.CL · stat.AP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12638

FAROS: Forecast-Aware Risk-Informed Online Reinforcement Learning for Proactive O-RAN Slicing

Peyman Eftekhari, Seyyed Kasra Mortazavi, Reza Farahani, Robert Legenstein, Kyandoghere Kyamakya, Martin Gebser

原文摘要

Proactive Open Radio Access Network (O-RAN) slicing requires decisions before an approaching quality-of-service (QoS) loss becomes difficult to reverse. We present FAROS, a Forecast-Aware Risk-Informed O-RAN Slicing framework that combines an eight-step QoS forecast, training-only PCMCI+-supported temporal risk, Multi-Agent Proximal Policy Optimization (MAPPO) under centralized training and decentralized execution (CTDE), symbolic feasibility constraints, and reliability-aware Top-K arbitration. MAPPO supplies the actor proposal, while A5v2 checks admissibility and one-step utility before execution. Evaluation uses ten validation-selected frozen checkpoints, 500 matched start indices per seed under the risky-start protocol, and 150,000 agent-level decisions. FAROS obtains mean reward 0.2778 and ten-step recovery 90.56% across ten seeds. A fixed model-matched diagnostic rule reaches reward 0.3015 and recovery 97.57% under the same transition-reward contract, so we make no superiority claim over direct threshold logic. A same-actor M4 shield control also reaches zero risky-state prohibited actions. In the M5 trace, A5v2 changes 22.61% of actor proposals and reduces the predicate-defined prohibited-action rate from 16.79% at proposal time to zero at execution; this property is enforced by the arbiter rather than learned by MAPPO. Independent ns-3 experiments test the six-action interface at packet level and remain separate from end-to-end FAROS claims.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12636

BioBind: Binding Biometric Deduplication to Zero-Knowledge Authentication

Taotao Wang, Xiaoxiao Wu, Shengli Zhang

原文摘要

Biometric identity systems for decentralized applications need credentials that resist repeated enrollment and support private, publicly verifiable authentication. Capture and large-scale private deduplication run off chain while smart contracts authorize issuance and use; these stages span distinct trust domains, and a correct verdict covers only the checked inputs and gallery snapshot. Without binding and state checks, concurrent enrollments can issue duplicate credentials from correct verdicts, while substituted inputs can authorize unrelated credentials. We present BioBind, a protocol whose four backend interface conditions bind the deduplication query, gallery insertion and issued commitment to one captured vector, authenticate gallery transitions, and require a sound uniqueness verdict valid at finalization. Its encrypted instance uses bound requests, stale-session rejection and committee-confirmed migration. Capture-bound zero-knowledge authentication links credential use to the enrolled template and a fresh device-originated probe bound to the challenge. We give a conditional multi-session composition argument under explicit capture, backend and cryptographic assumptions. A prototype using LFW face features rejects the tested composition attacks; its unlinkable authentication circuit uses 31,445 constraints and about 305,000 gas. An equal-public-field baseline quantifies the cost of verifiable matching: witness-plus-proving medians are 1.989 s versus 1.119 s with device-trusted matching. Separate tests of encrypted enrollment complete three histories of 16,384 registrations without decoding errors at the tested checkpoints. Biometric accuracy bounds person-level uniqueness: on the Bosphorus database, cooperative subjects who change appearance evade deduplication in 1.8% of re-enrollment attempts at the operating threshold. Full backend integration remains open.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36143

Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security

Leo Benaharon, Chi Zhang, Wei Zheng, Weifan Zhang, Yifan Wei, Yong Sun

原文摘要

Coding agents can adapt robotic software by revising executable programs, but successful responses to an evolving opponent may not remain effective. We present a framework for program-level adversarial co-adaptive self-play in which coding agents generate attacks and defenses from tested opponent code and mission feedback, without model fine-tuning. Environment-specific interfaces support external programs for autonomous driving and SDK-level defenses for humanoid locomotion. Two eight-generation case studies reveal concrete software responses: a driving defender introduces direct-actuation recovery, while a humanoid defender revises incoming-state validation. These responses provide local task recovery but do not establish sustained robustness. The framework makes such adaptation and limitations observable through executable artifacts and task-level evidence.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12635

Beyond Sunny Skies: Using Large Language Models to Predict Urban Traffic in Adverse Weather

Zhu Xiao, Kuan Feng, Tong Li, Chenxi Liu, Gang Wang, Zhuo Tang, Kenli Li

原文摘要

Urban traffic flow prediction is a cornerstone of intelligent transportation systems, yet accurate forecasting under adverse weather conditions remains a significant challenge. Existing data-driven models, while effective for routine patterns, often struggle with the sparse data and complex non-linear shifts associated with rare meteorological events. These methods typically treat environmental contexts as shallow numerical features, failing to capture the underlying semantic reasoning-why and how specific adverse conditions alter mobility behaviors across regions with different functional compositions. To address this limitation, we propose Multi-STG, a unified framework that integrates Large Language Model (LLM)-derived semantic priors with graph-based spatiotemporal learning. Multi-STG introduces an LLM-empowered semantic enhancement module that transforms comprehensive context descriptions such as weather, POIs, and holidays into high-level semantic embeddings, effectively providing a knowledge-driven complement to data scarcity. Furthermore, we design a multimodal attentional fusion mechanism to dynamically weigh heterogeneous inputs and a semantic-enhanced prediction head with gated residual calibration to robustly adjust forecasts based on semantic guidance. Extensive experiments on real-world multi-city private car datasets demonstrate that Multi-STG outperforms state-of-the-art baselines, reducing MAE by 11.82\% on average relative to the strongest baseline across three cities, while maintaining stable performance under sparse and non-stationary conditions.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.12300

Internet-Scale Measurement of React2Shell Exploitation Using an Active Network Telescope

Aakash Singh, Kuldeep Singh Yadav, Md Talib Hasan Ansari, V. Anil Kumar

原文摘要

The increasing adoption of server-side component-based web frameworks has introduced new application-layer attack surfaces that remain insufficiently understood at Internet scale. On 3 December 2025, a critical remote code execution vulnerability (CVE-2025-55182) in React Server Components, referred to as React2Shell, was publicly disclosed and subsequently observed being exploited in the wild. Despite its critical severity and a CVSS base score of 10.0, there is limited empirical understanding of how this vulnerability is exploited across the Internet. This paper presents the first Internet-scale measurement study of React2Shell exploitation activity using traffic collected from an Active Network Telescope. We developed a deterministic detection methodology that identifies exploitation attempts targeting endpoints implementing React Server components. It helped analyze exploitation traffic to characterize its temporal evolution, geographic and autonomous system-level distribution, and behavioral properties of the observed scanning activity. In addition, exploit payloads are examined to understand the attacker infrastructure and delivery mechanisms. The analysis reported rapid post-disclosure exploitation activity exhibiting patterns consistent with automated scanning campaigns, geographically distributed scanners, and concentrated backend infrastructure. To the best of our knowledge, this work provides the first quantitative characterization of React2Shell-triggered scanning activity, including the number of distinct scanners, their geographic and autonomous system distribution, and the scale of backend infrastructure involved in exploitation attempts.

cs.CR · cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.04736

Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates

Thatchanon Anancharoenkij, Donlapark Ponnoprat

原文摘要

A complete understanding of heterogeneous treatment effects requires fully capturing the conditional distribution of the counterfactual outcomes. To this end, we propose the Conditional Counterfactual Mean Embeddings (CCME), a framework that embeds conditional distributions of counterfactual outcomes into a reproducing kernel Hilbert space (RKHS). Under this framework, we develop a two-stage meta-estimator for CCME that accommodates any RKHS-valued regression in each stage. Based on this meta-estimator, we develop three practical CCME estimators: (1) Ridge Regression estimator, (2) Deep Feature estimator that parameterizes the feature map by a neural network, and (3) Neural-Kernel estimator that performs RKHS-valued regression, with the coefficients parameterized by a neural network. We provide finite-sample convergence rates for all estimators, establishing that they possess the double robustness property. Our experiments demonstrate that our estimators accurately recover distributional features including multimodal structure of conditional counterfactual distributions. Our code is available at https://github.com/donlap/Conditional-Counterfactual-Mean-Embeddings.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.26515

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

Hei Yi Mak, Shadan Golestan, Hoang Le, Mehran Taghian Jazi, Yunke Peng, Yaoyuan Wang, Yao Wang, Junsong Wang 等 13 位作者

原文摘要

We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision. A systematic study reveals that the dominant source of degradation in FP4 RL is not training-side quantization error but rollout activation quantization: outliers stretch the dynamic range so far that a large number of activation values underflow to zero under FP4. Counterintuitively, restoring the training policy to higher precision while keeping the rollout in FP4 makes accuracy worse than full FP4 baseline, exposing rollout--training mismatch as the principal failure mode and ruling out standard pretraining-style fixes. We address this with Rollout Residual Quantization (Rollout-ResQ): a single residual correction term constrained to a hardware-friendly sparsity pattern, added only to the FP4 rollout matmul -- a lightweight correction that recovers most of the precision lost to outlier-driven underflow without inflating the rollout's compute footprint. On Qwen2.5-3B, Rollout-ResQ paired with the HiFloat4 (HiF4) format -- whose three-level hierarchical scaling preserves resolution under FP4's tight 4-bit budget -- closes the accuracy gap to BF16 from 3.59% to 1.39%, bringing fully quantized FP4 RL within close reach of full precision. Applied to the open-standard MXFP4, the same recipe narrows the gap from 13.6% to 5.3%, revealing that FP4 format choice is a key factor that determines the ceiling on recoverable accuracy. The experimental results on Qwen2.5-Math-7B further confirm the recovery benefits of Rollout-ResQ with HiF4. Together, these results establish HiF4 as the enabling format for end-to-end FP4 RL post-training, and Rollout-ResQ as the activation-side mechanism that makes the gap to BF16 closable.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12628

Adapting Small Language Models to Romanized Nepali: Tokenizer Fertility, Reference Likelihood, and Generation Metrics

Pujan Pant, Sagar Newpane, Hari Sitaula, Manish Sakhakarmy

原文摘要

Romanized Nepali, Nepali written in Latin script, is common in digital communication but has no standard spelling and few resources, and it is unclear how reliably small open language models can be adapted to it. We adapt three 2-3B base models from different families, Llama-3.2-3B, Qwen2.5-3B, and Gemma-2-2B, with QLoRA on 9,000 instruction examples produced by deterministic transliteration of Nepali instruction data. Each model is trained with one shared recipe and three seeds and evaluated on 1,000 held-out examples with reference-overlap metrics, byte-normalized reference likelihood (bits per byte, BPB), and an output audit, against zero-shot baselines under two prompts. Fine-tuning raises chrF++ from 10-14 to 29.0-30.6 and lowers BPB from 2.23-2.41 to 0.78-0.84; most zero-shot outputs (54-92%) are English-like. Likelihood and overlap disagree on how far apart the models are. Llama-3.2-3B has the lowest BPB in every seed, 0.042 below Qwen2.5-3B (95% CI 0.039-0.046), yet the two cannot be separated on chrF++ (30.51 and 30.61) or BLEU, even with paired item-level tests. Gemma-2-2B, whose tokenizer splits Romanized Nepali words least (2.72 tokens per word), scores worst on every measure. Which model gains most over its zero-shot baseline depends on the zero-shot prompt. In a supplementary comparison with an identical tokenizer, Llama-3.1-8B lowers BPB by 0.053 (0.050-0.056) relative to Llama-3.2-3B, while chrF++ and BLEU rise by only 0.68 and 0.58 points. Lower fertility and higher reference likelihood therefore did not identify the model whose outputs were closest to the references.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.09489

Ceci n'est pas une pipe: A semantics of justified reliance for AI systems

Jade Alglave, Patrick Cousot

原文摘要

An AI agent may keep a successful check in context after an edit has invalidated its evidence. We give a semantics for specifying when a system may rely on a message and act on it. Reliability checks an asserted claim against accepted domain knowledge, sources, and messages in the selected context. Justified reliance additionally checks current evidence, authority, and the proposed world change. Relational component semantics and event traces represent nondeterministic outputs, iteration, and external changes. We characterise when merging claims preserves derivable conclusion classes, then construct the coarsest permitted quotient whose rules preserve the exact statuses of designated concrete claims. Construction is polynomial for unary rules; deciding even one permitted merge is coNP-complete for acyclic binary rules. This applies completeness and strong-preservation methods to the execution of quotiented rules. We also relate transition safeguards to runtime enforcement. Relative to a supplied set of possible worlds, a sound guard accepts an observation only when every matching world passes the checks. Exact acceptance requires observations that distinguish opposite-decision worlds; choosing sufficient services is NP-complete on explicit finite tables. A complete finite passport-renewal instance, Lean theorem encodings, Z3 instance checks, and an OCaml harness exercise the semantics. Domain knowledge, interpretation, source licenses, and policy remain application inputs.

cs.AI · cs.PL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.11288

Memorization and Malign Generalization in Conditional Diffusion Models with Random Features

Gwangho Kim, Sungyoon Lee

原文摘要

Conditional diffusion models generate diverse, novel, and high-quality samples under prescribed conditions. However, theoretical understanding of their memorization and generalization remains limited, while recent works have characterized these behaviors primarily in unconditional settings. In this work, we analyze a random-feature conditional score model in the high-dimensional proportional limit, deriving asymptotic expressions for training and test losses. By decomposing the test loss, we show that in the overparameterized regime, increasing model width improves prediction of the condition-dependent mean while reducing within-condition prediction variance, a phenomenon we term "malign generalization." We further show that in the infinite-width limit, the model predicts the conditional mean as accurately as ridge regression of the data on the condition, while its within-condition variance vanishes. Finally, analyzing the training loss reveals that more informative conditions lead to memorization of training samples at smaller widths. These theoretical findings are supported by experiments with U-Net architectures on realistic data.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.10103

LLM Watermarking as Big Data Provenance: A Deployment-Oriented Systematization

Huy Phan, Kieu Dang, Ojaswi Dulal, Aiham AL Shukairi, Abby Shine, Chase Garner, Phung Lai

原文摘要

As large language models (LLMs) generate and transform content at scale, reliable attribution becomes an increasingly important requirement for big data provenance. Although numerous watermarking methods have been proposed, existing evaluations predominantly emphasize sample-level detectability and robustness, leaving deployment requirements such as serving efficiency, population-scale false positives, multi-key attribution, and long-term verification less systematically examined. This paper presents a deployment-oriented systematization of LLM watermarking through the five Vs of big data: Volume, Velocity, Variety, Veracity, and Value. We classify representative watermarking methods across four dimensions: insertion point, verification authority, operational state, and adversarial threat model. We further map these methods to four deployment workloads: online generation, streaming detection, transformation pipelines, and ecosystem governance. Our synthesis identifies recurring limitations, including dependencies on generation-time access, additional inference overhead, sensitivity to downstream transformations, and incomplete reporting of calibration and lifecycle compatibility. Based on these findings, we propose workload-specific evaluation requirements covering statistical reliability, throughput, utility, robustness, and governance. This framework connects watermark design choices to practical deployment constraints and provides guidance for selecting and evaluating provenance mechanisms in large-scale data ecosystems.

cs.CR · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12619

Better Bounds For Graph Reconstruction

Antoni Buraczewski, Paweł Gawrychowski

原文摘要

The goal in graph reconstruction problems is to learn an initially unknown graph using only a few queries of a specific type. Possibly the most natural query type is retrieving the distance between any two vertices of a connected, undirected, and unweighted graph. For a bounded-degree graph on $n$ vertices, Kannan, Mathieu, and Zhou [TALG 2018] showed a randomized algorithm that uses only $\tilde{\mathcal{O}}(n^{3/2})$ such queries. On the lower bound side, it is only known that any randomized algorithm needs $Ω(n\log n)$ queries. We make a significant step forward to bridging these bounds by designing a randomized algorithm that uses $n^{4/3+o(1)}$ queries. This requires extending the original approach based on Voronoi diagrams into a recursive procedure that partitions a cell into smaller cells. While such a recursive approach has been used in the related graph verification problem, in the more general graph reconstruction problem we need to operate without knowing the graph, which requires a new (and more technical) approach.

cs.DS · cs.DM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.26379

When Does LeJEPA Learn a World Model?

David Klindt, Yann LeCun, Randall Balestriero

原文摘要

A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaussian regularization) linearly recovers the world's latent variables from nonlinear observations, a property known as linear identifiability, in a class of worlds where latents evolve under stationary, additive-noise transitions. Our main result is that among all such worlds, the Gaussian is the unique latent distribution for which this guarantee holds. The forward direction rests on a spectral decomposition in which each degree of nonlinearity is strictly penalized by alignment, making the linear map the optimum; the converse rules out every non-Gaussian alternative. We further prove an approximate identifiability result where the guarantee degrades gracefully, and show that linear, orthogonal identifiability enables optimal latent-space planning. We validate the theory with experiments ranging from 2D examples to 4096-dimensional latents, including ablations, pixel-based robotic control, and natural images from ImageNet-X. Our theory turns an empirically successful recipe into a mathematical guarantee, providing the foundation for building World Models that provably recover the structure of the world.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.27710

FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology

Anh-Tien Nguyen, Trung Dang, Nghiem Tuong Diep, Bui Ngoc Han Nguyen, Tan-Ha Mai, Miriam Cindy Maurer, Phuong Hoa Nguyen, Thi Thuy Uyen Nguyen 等 12 位作者

原文摘要

Pathology vision-language foundation models vary in performance across diseases and tasks, with no single model consistently performing best. The high cost of expert pathology annotation can also limit the labeled data available for task-specific adaptation. Combining complementary pretrained representations is a potential approach to these limitations, yet learning an effective fusion from few labeled examples remains challenging. We introduce Few-shot Fusion Foundation Models of Computational Pathology (FFM-CP), which is a framework that combines multiple pathology vision-language models in the few-shot learning setting. The framework first aligns heterogeneous representations using a closed-form Orthogonal Procrustes transformation estimated from corresponding support images. This alignment preserves within-model feature geometry without training an additional alignment network. Within the aligned space, a unified graph enables information exchange across backbones by jointly refining support-image features and visual and textual class prototypes. These refined representations support complementary text-prototype and case-retrieval branches that capture semantic class knowledge and within-class visual variation, respectively. Each branch learns to combine predictions from all ordered backbone pairs, allowing queries encoded by one model to draw on evidence represented by another. We evaluate three backbone combinations on six histopathology datasets at 4, 8, and 16 shots per class. FFM-CP achieves higher mean macro-F1 than the strongest individually adapted member of each fused set in 50 of 54 comparisons. These findings suggest that combining complementary pretrained representations can improve histopathological classification when annotations are limited.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.20708

ALICE-LRI: A General Method for Lossless Range Image Generation for Spinning LiDAR Sensors without Calibration Metadata

Samuel Soutullo, Miguel Yermo, David L. Vilariño, Óscar G. Lorenzo, José C. Cabaleiro, Francisco F. Rivera

原文摘要

3D LiDAR sensors are widely used in autonomous navigation, environmental monitoring, and precision mapping. Their point clouds are often projected into 2D range images for efficient processing, but conventional projection methods can lose points because of geometric inconsistencies. We present ALICE-LRI (Automatic LiDAR Intrinsic Calibration Estimation for Lossless Range Images), a metadata-free method for lossless range-image generation from calibrated spinning multi-beam LiDAR point clouds. It requires neither factory calibration files, packet-level data, nor beam identifiers, and targets operating regimes where scanlines contain enough returns for reliable parameter estimation. The method estimates the intrinsic calibration parameters relevant to projection, including beam configuration, angular distributions, and per-beam geometric corrections. Evaluation on the complete KITTI and DurLAR datasets yielded zero lost points across all point clouds. Reconstruction deviations remain below manufacturer-reported range-performance specifications, while the method runs in real time. A compression case study also shows improved reconstruction quality and a better quality-compression trade-off for a downstream application. These results enable range-image-based LiDAR processing in applications that require high measurement fidelity and preservation of acquired geometric information.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2204.00920

Deep Algebraic Fitting for Multiple Circle Primitives Extraction from Raw Point Clouds

Zeyong Wei, Honghua Chen, Hao Tang, Qian Xie, Mingqiang Wei, Jun Wang

原文摘要

The shape of circle is one of fundamental geometric primitives of man-made engineering objects. Thus, extraction of circles from scanned point clouds is a quite important task in 3D geometry data processing. However, existing circle extraction methods either are sensitive to the quality of raw point clouds when classifying circle-boundary points, or require well-designed fitting functions when regressing circle parameters. To relieve the challenges, we propose an end-to-end Point Cloud Circle Algebraic Fitting Network (Circle-Net) based on a synergy of deep circle-boundary point feature learning and weighted algebraic fitting. First, we design a circle-boundary learning module, which considers local and global neighboring contexts of each point, to detect all potential circle-boundary points. Second, we develop a deep feature based circle parameter learning module for weighted algebraic fitting, without designing any weight metric, to avoid the influence of outliers during fitting. Unlike most of the cutting-edge circle extraction wisdoms, the proposed classification-and-fitting modules are originally co-trained with a comprehensive loss to enhance the quality of extracted circles.Comparisons on the established dataset and real-scanned point clouds exhibit clear improvements of Circle-Net over SOTAs in terms of both noise-robustness and extraction accuracy. We will release our code, model, and data for both training and evaluation on GitHub upon publication.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.09271

Zero-Shot Weight-Space Programming Across a Difficulty-Graded Ladder of Two-Player Games

Eduardo C. Garrido-Merchán

原文摘要

Weight-space programming sets every weight of a feed-forward network by hand, from an explicit specification of the desired computation, with no gradient descent and no training data anywhere in the construction. We ask how far a large language model can carry this practice, zero-shot, across games of deliberately increasing difficulty. We design a four-rung ladder (Nim, tic-tac-toe, two sizes of Connect Four, and a chess endgame) spanning four axes of difficulty, and build a second, independent network at each rung, using a structurally unrelated game at matched difficulty, to separate what a rung's finding says about the difficulty level from what it says about the one game used to measure it. Ten networks are built and independently verified. Six admit a complete, non-statistical proof of correctness against an independent oracle. The chess-endgame rung is exact where correctness is cheap, move legality and, in one network, an exact one-ply mate detector, and collapses where it is expensive, composing a multi-move mating plan, from 84.1-100% success at the one-ply tactics it was built to get right down to 0.57-9.13% in full adversarial play; its replicate shows this collapse is an order of magnitude less severe under a shorter required plan and exact rather than heuristic safety checks. The standard-sized rung confirms, by holding hand-set evaluation weights fixed and adding only shallow search, that the remaining gap is an architectural ceiling rather than a matter of engineering effort, and this exact collapse reproduces across two structurally unrelated games. We release all ten networks, their independent oracles, construction-cost measurements, and a cold-prompt protocol for a future cross-model comparison

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.08446

AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly

Zhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian, Jiateng Liu

原文摘要

Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachment relations into 6D pose updates that enable parts to physically interact with the environment and previously assembled components. To study this problem, we propose AssemState, a zero-shot framework for manual and physical-state-guided furniture assembly. It firstly employs anchor-guided boundary assembly states to decompose manual pages into single-part operations and recover an assembly-tree. Then, it uses iterative after-state feedback refinement to guide successive (SE(3)) updates and corrections, and validates their physical plausibility through simulation-based release tests. Experiments show that compared with the strongest prior baseline, AssemState improves F1 from 38.58\% to 62.80\% and Tree Exact Match from 28.24\% to 53.92\% for assembly-tree recovery. On 243 independently evaluated part-level operations, our proposed iterative refinement improves judge-accepted operations from 0 to 5.3\% and reduces mean Chamfer distance from 5.4111 to 1.7744. However, visually plausible candidate poses may still suffer from collision, floating, mirror-orientation errors, incomplete seating, and wrong-side attachment. These results show that AssemState improves operation-structure recovery and selected local pose metrics, while MLLMs remain limited for spatial relationship reasoning.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12604

Double Blind Evals: Resolving the Dual Confidentiality Dilemma in AI Safety Auditing

Andrew Trask, Sol Messing, Vai Pahwa, Pegah Maham, Rene Kolga, Austin Frantz, Andrew Tash, Kate Thomas 等 30 位作者

原文摘要

AI safety evaluations often involve sensitive prompts and proprietary models. Evaluators want to keep their evaluation prompts secret from model owners to prevent purposeful or incidental data leakage, ensuring longer usefulness of their benchmark. Model owners in turn wish to keep their proprietary model weights and inference code within their own secure infrastructure to protect their IP. We present a way forward for "double-blind evals", which provide cryptographic guarantees that an evaluator's prompts are not shared with the model owner, while simultaneously maintaining the confidentiality of the model weights and inference code. To accomplish this, we use secure enclaves that encrypt data in RAM at the hardware level. In a world-first pilot, we test this approach by evaluating a proprietary Google DeepMind model (Gemini 2.5 Flash Lite) against a selection of the private AILuminate benchmark corpus, using an NVIDIA H100 secure enclave on Google Cloud Platform, and using OpenMined's PySyft to maintain data and model privacy. We believe this effort marks the first use of this technology to provide mutual secrecy for one organization's frontier-class proprietary model weights and another organization's closed benchmark.

cs.CR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12603

Direct Conditioning of Audio Diffusion Transformers on fMRI Reveals Cortical Contributions to Sound Reconstruction

Matteo Ciferri, Tonio Weidler, Matteo Ferrante, Nicola Toschi, Elia Formisano

原文摘要

Reconstructing audio from brain activity remains challenging. Existing brain-to-audio pipelines typically map neural responses to predefined stimulus representations before synthesis. While recent work in the visual domain has explored direct conditioning on brain activity, this approach has not yet been extended to audio diffusion models. We introduce MAAS (Multi-Area Auditory Synthesis), an end-to-end framework that conditions a pretrained audio diffusion transformer on ROI-wise fMRI responses without first supervising a decoder to predict an external stimulus representation. MAAS uses region-specific projections and learned brain tokens to condition Stable Audio through a dedicated cross-attention pathway. On a 7T fMRI dataset, we demonstrate consistent improvements over baselines, including two-stage fMRI-to-latent conditioning, across both acoustic and semantic evaluation metrics. In addition, we introduce a fidelity metric grounded in a computational model of auditory neural processing, which allows us to quantify the contribution of individual auditory cortical regions to reconstructed audio representations.

cs.SD · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.09541

Memory-Efficient Active Perception for Embodied Question Answering in Dynamic Human-Populated Scenes

Xin Lu, Rui Li, Xun Huang, Weixin Li, Jiayuan Li, Chuanqing Zhuang, Zhengda Lu, Jun Xiao

原文摘要

Embodied Question Answering (EQA) couples active visual perception, vision-language reasoning, and sequential decision making, and has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. In realistic multimedia settings such as dynamic human-populated scenes, however, moving people and transient occlusions introduce human-induced perceptual variations: task-relevant multimodal cues become transient, viewpoint-dependent, and incompletely captured in individual views. Conventional store-then-retrieve strategies generate redundant visual evidence and incur high inference cost, making them ill-suited to such variations. This exposes two core problems for embodied agents: resolving viewpoint-dependent ambiguity, and maintaining compact evidence for efficient inference. To address these challenges, we present DIVRR (Dynamic-Informed View Refinement with Relevance-guided Rotation and adaptive memory selection), a training-free active evidence-acquisition framework for EQA. DIVRR combines question-conditioned room guidance with relevance-triggered view augmentation to guide exploration and additional observation. Selective memory admission uses the same relevance signal as view augmentation to retain high-scoring evidence, reducing stored entries while keeping the retrieved visual context compact. To evaluate EQA under human-induced perceptual variations, we introduce DynHuman-EQA, a dynamic human-populated EQA dataset constructed in Habitat, comprising dynamic and static subsets under shared scene layouts. Experiments on DynHuman-EQA and HM-EQA show that DIVRR outperforms existing baselines in both accuracy and memory efficiency. The gains are most pronounced in dynamic human-populated scenes.

cs.CV · cs.MM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12600

Reducing Provers in Distributed Quantum Verification

Alex Della Schiava, Atsuya Hasegawa, François Le Gall, Harumichi Nishimura

原文摘要

In the distributed quantum Merlin-Arthur ($\mathsf{dQMA}$) model introduced by Fraigniaud, Le Gall, Nishimura, and Paz (ITCS 2021), a network of quantum computers verifies a global property with the aid of a quantum proof supplied by an untrusted prover. While the nodes are computationally unbounded, the challenge is to limit proof size and the communication required for verification. In this paper, we consider the model of Hasegawa, Kundu, and Nishimura (PODC 2024), where the proof must be unentangled across nodes, and define its extension to $k$ unentangled provers, denoted by $\mathsf{dQMAS}(k)$. In this setting, we investigate the proof size per node and the communication costs of reducing the number of provers. Our first result reduces the number of provers from $k$ to two, doubling the proof size without additional communication. Moreover, with four additional rounds, we can reduce the number of provers from $k$ to one, using at most three times the original local proof size plus a logarithmic term in the number of nodes. Finally, we establish amplification for perfectly complete protocols. In this regime, a single prover suffices with a constant-factor overhead in our reductions, yielding $\mathsf{dQMAS} = \mathsf{dQMAS}(k)$.

quant-ph · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12599

Consistent Mapping for Fluid Structure Interaction with Geometrically Nonlinear Isogeometric Beams

Juan Ignacio Camarotti, Ricky Aristio, Roland Wüchner

原文摘要

Isogeometric beam formulations provide an efficient reduced-dimensional representation of slender structures, combining accurate geometry and high-order continuity with few structural degrees of freedom. Their application to fluid--structure interaction (FSI) requires transferring motion and loads between the one-dimensional beam centerline and the surrounding fluid interface. While mapping strategies exist for conventional finite element beams, geometrically nonlinear isogeometric formulations require operators consistent with their spline-based kinematics and distinct descriptions of cross-sectional rotation. This work develops consistent beam-to-surface mappings for geometrically nonlinear isogeometric Bernoulli and Timoshenko beams in partitioned FSI. Fluid-interface points are attached to the beam in the reference configuration and reconstructed using the nonlinear kinematics of each formulation. Consistent linearization yields a configuration-dependent mapping operator whose transpose ensures work-conjugate load transfer. The formulations are verified through analytical deformation tests, convergence studies, and virtual-work checks, and evaluated in beam-based adaptations of the Mok and Turek--Hron benchmarks and the Goland wing flutter benchmark. The results confirm accurate interface reconstruction and work-conjugate load transfer under large deformations, while demonstrating the applicability of both beam formulations to coupled FSI problems.

physics.comp-ph · cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12597

Unmasking Four Knapsack Problems in the Traveling Thief Benchmark

Mohammed Mizan Alanazi, Mahdi Khemakhem

原文摘要

The traveling thief problem (TTP) asks a thief to choose a tour and a packing together, and the benchmark of 9,720 instances of Polyakovskiy et al. (2014) is the standard test set for comparing TTP heuristics. We show that four of these instances are not TTP instances at all. Their files give a renting rate of 0.00, so the tour has no effect on the objective and each instance reduces to a 0-1 knapsack problem. One of them belongs to the 60 categorized instances on which new methods are usually compared, and on it five of nine published methods report exactly the same value. The cause is the format of the files, which keep the renting rate with two decimals, while the rule of the generator gives a rate close to 0.003 on these instances. The same rounding may shift the rate of 949 other instances by more than 1%. Since the tour and the packing used by the generator were not published, the original rates cannot be recovered. We therefore define new rates with the same rule, applied to a fully specified reference solution that we publish, and we show with a published heuristic that the corrected instances behave as TTP instances again. We also give reference results on the corrected instances and recommendations for future studies. Finally, we present ttplib, a new open-source Python library that loads any of the 9,720 instances, including the corrected ones, without downloading the whole benchmark.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗